chettriyuvraj Posted November 21, 2021 Posted November 21, 2021 I will be digitizing(scanning) [ICU Graphs][1] i.e over which patient vitals will be plotted(eg. heart rate wrt time) using a machine learning model. However the lines may need to be 'nudged' up and down sometimes by a person (a human-in-the-loop) to correct them. The approach will be similar to how we move the lines to [crop an image in camscanner][2] i.e user only move the vertices. How can we go about implementing the UI(say in a JS framework like Angular/React) to allow the user to move these lines up and down and correct them? [1]: https://i.stack.imgur.com/iEHqL.png [2]: https://i.stack.imgur.com/ghG6S.png
Gianni Posted November 21, 2021 Posted November 21, 2021 Do you want to change and correct the scan area set automatically by the program before scanning? what software do you use to digitize the image? Chimp small minds discuss people average minds discuss events great minds discuss ideas.... and use AutoIt....
chettriyuvraj Posted November 28, 2021 Author Posted November 28, 2021 Hi! First things first, thanks for the reply! 1. No. The corrections are to be made by an actual person post scanning using a UI tool. The lines will be plotted over the scanned image by a program/ML model - these plottings might have minor mistakes which the user must correct by grabbing hold of the vertices and moving the lines up/down. (How should the lines be plotted? Something like an HTML Canvas with the graph as the background over which lines are plotted?) 2. No decision over the software that is to be used for digitizing. Open to suggestions/changing the approach. The discussions are at a very nascent stage and I am looking for a quick feasibility check in terms of the UI side of the problem.
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now